Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1926. Min Act: -0.0000

Data Index: 390482 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1739300 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1048993 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1195. Min Act: -0.0000

Data Index: 989893 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1919024 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.2222. Min Act: -0.0000

Data Index: 980267 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1389. Min Act: -0.0000

Data Index: 449821 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1827. Min Act: -0.0000

Data Index: 580519 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1326359 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1019. Min Act: -0.0000

Data Index: 593956 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0281. Min Act: -0.0000

Data Index: 491957 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1059. Min Act: -0.0000

Data Index: 699532 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1081722 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1246176 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0258. Min Act: -0.0000

Data Index: 647336 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1859182 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1049996 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1637733 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0618. Min Act: -0.0000

Data Index: 899257 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1338228 (The Pile)

Max Activating Token Index: 369